© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68962
    Prev
    Next
    INDEX
    Explanations

    Parsons name, loft spaces, hashCode function

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron is essentially firing on any token containing the character sequence “pars” (e.g. “Parsons,” “parson,” “Pars” in “pars plana,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vuelven
    -3.00
    罽
    -2.95
    哢
    -2.77
    䊐
    -2.67
    ⃢
    -2.66
    呿
    -2.64
    媗
    -2.58
     llevan
    -2.44
     khawatir
    -2.39
    퐹
    -2.39
    POSITIVE LOGITS
    5
    2.75
    In
    2.75
    Y
    2.63
    (
    2.59
     Theore
    2.48
    The
    2.47
     Saying
    2.39
    st
    2.39
    2
    2.36
    –
    2.34
    Activations Density 0.002%

    No Known Activations